Ramunė Kasperė

ABSTRACT

Researchers agree that machine translation (MT) quality in many language pairs is still far from publishable (Koponen, 2016). However, machine translation post-editing has become a routine practice in the translation industry worldwide. The purpose, domain and MT quality determine the post-editing effort exerted by a linguist/translator for the preparation of the final text. This study aims at finding out the post-editing effort needed to produce a near-human publishable quality, or in other words, full post-editing quality of machine translated text in the English-to-Lithuanian language pair. The research conclusions are made based on two different types of post-editing effort indicators defined by Krings (2001) in his ground-breaking work (Castilho et al., 2018), i.e., temporal (time spent) and technical (number of edits), as well as post-edit actions (PEA), following Blain et al.’s (2011) PEA typology. The data for analysis are obtained via a screen recording experiment using TRANSLOG-II, a programme recording human writing processes (Carl, 2012). This study is the first attempt to analyse the post-editing effort following neural machine translation performed in Lithuanian as a morphologically rich, yet under-resourced, language. The study demonstrates some insightful results that may be beneficial for translator and post-editor trainers from the pedagogical and theoretical perspectives as well as for translation industry representatives from the practical perspective.

Keywords

Machine translation; post-editing; temporal effort; technical effort; post-edit actions

References

1. Blain, F., Senellart, J., Schwenk, H., Plitt, M., & Roturier, J. (2012). Qualitative analysis of post-editing for high quality machine translation. Machine Proceedings of the 13th Machine Translation Summit (pp. 164–171).

2. Carl, M. (2012). Translog - II: A program for recording user activity data for empirical reading and writing research. In Proceedings of the Eight International Conference on Language Resources and Evaluation, European Language Resources Association (ELRA).

3. Castilho, S., Doherty, S., Gaspari, F., & Moorkens, J. (2018). Approaches to human and machine translation quality assessment. In J. Moorkens J., at al. (Eds.), Translation Quality Assessment. Machine Translation: Technologies and Applications (pp. 9–38).

4. Koponen, M. (2016). Is machine translation post-editing worth the effort? A survey of research into post-editing and effort. The Journal of Specialised Translation, 25, 131–148.

5. Krings, H.P. (2001). Repairing Texts: Empirical Investigations of Machine Translation Post-Editing Processes. Kent: Kent State University Press.